Agents & Evals
How to build agents, and how to tell whether they actually work.
To read · 10
Why KamiBench for continual learning
KamiBencharticle
What agents remember
KamiBencharticle
AI Agents That Matter
Kapoor et al.paper
Measuring AI Ability to Complete Long Tasks
METRarticle
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
Princeton HALpaper
Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
Andon Labspaper
AI Village
AI Digestarticle
Alpha Arena
Nof1article
τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Sierrapaper
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
Xu et al.paper